import re
from html_downloder import HtmlDownloader
from html_downloder import Image

"'起始URL'"
url = "https://www.douban.com"
"'保存目录'"
image_path = "F:\source\Python\爬虫\ImageGet\Image%s.jpg"
"'定义实体类'"
downloader = HtmlDownloader()
html = downloader.download(url)
"'SaveFile(html, html_path)'"
html = html.decode('utf-8')
"'正则表达式'"
reg1 = r'="(https://img[\S]*"'
"'提取图片的URL'"
dbdata = re.findall(reg1, html)
imgsave = Image()

"'下载保存图片'"
imgsave.ImageGet(dbdata, image_path)

 # file: html_downloader.py
 
 import urllib.request
 import urllib.error
 import time

 class HtmlDownloader(object):
  def download(self, url):
   if url is None:
    return None
   try:
    header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)'}
    "'发出请求'"
    request = urllib.request.Request(url=url, headers=header)
    "'获取结果'"
    response = urllib.request.urlopen(url)
   except urllib.error.URLError as e:
    if hasattr(e, "code"):
     print(e.code)
    if hasattr(e, "reason"):
     print(e.reason)
   if response.getcode() != 200:
    return None
   html = response.read()
   response.close()
   return html

 class Image (object):
  def ImageGet(self, imageurl, image_path):
   x = 0
   for li in imageurl:
    urllib.request.urlretrieve(li, image_path % x)
    x = x + 1
    "'休眠5s以免给服务器造成严重负担'"
    time.sleep(5)